© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72913
    Prev
    Next
    INDEX
    Explanations

    framework va q main

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on programming identifiers—especially library or macro names written in uppercase or CamelCase (e.g., “Framework” or “VA”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     With
    -1.94
     for
    -1.91
    焊接
    -1.67
     çoğu
    -1.66
     bazı
    -1.65
    r
    -1.65
     refugi
    -1.63
     contado
    -1.62
    してない
    -1.61
     özellikle
    -1.59
    POSITIVE LOGITS
    ſſer
    2.09
    牐
    1.99
    “
    1.96
    
    1.95
    3
    1.90
    ⬯
    1.89
     całym
    1.87
     هاي
    1.80
     эту
    1.79
     エロ
    1.78
    Activations Density 0.000%

    No Known Activations